Claude Opus 4.5 vs Gemini 3.1 Pro
Claude Opus 4.5 (Anthropic) and Gemini 3.1 Pro (Google DeepMind) compared on benchmarks, pricing, context window, and use-case rankings.
- Gemini 3.1 Pro leads on overall intelligence (ECI 155 vs 150).
- Claude Opus 4.5 ranks higher for coding (72th vs 65th percentile).
| Attribute | Claude Opus 4.5 | Gemini 3.1 Pro |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 150 | 155 |
| Coding | 72 | 65 |
| Math | 31 | 74 |
| Reasoning & Knowledge | 63 | 94 |
| Agentic & Tools | 63 | 83 |
| Specifications | ||
| Developer | Anthropic | Google DeepMind |
| Family | Claude | Gemini |
| Released | Nov 24, 2025 | Feb 19, 2026 |
| Parameters | — | — |
| Availability | API access | API access |
| Context window | 200K | — |
| Price — $/M input | $5.00 | — |
| Price — $/M output | $25.00 | — |
| Inputs | file, image, text | — |
| Outputs | text | — |
| Benchmarks | ||
| AIME 2024/2025 | 86% | 96% |
| APEX | 21% | 34% |
| ARC-AGI | 80% | 98% |
| ARC-AGI-2 | 38% | 77% |
| FrontierMath | 21% | 37% |
| FrontierMath Tier 4 | 4% | 17% |
| GDPval (win/tie rate) | 60% | — |
| GPQA Diamond | 86% | 94% |
| GSO (code optimization) | 27% | 23% |
| Humanity's Last Exam | 25% | 46% |
| LiveCodeBench | 87% | — |
| METR task horizon | 4.9 h | 6.4 h |
| MMLU-Pro | 90% | — |
| SciCode | 50% | — |
| SimpleBench | 62% | 80% |
| SimpleQA Verified | 42% | 77% |
| SWE-bench Verified | 77% | 76% |
| Terminal-Bench | 63% | 80% |
| WebDev Arena | 1512 | 1461 |
| WeirdML | 64% | 72% |
| τ²-bench | 89% | — |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Is Claude Opus 4.5 better than Gemini 3.1 Pro?
On Epoch AI's Capabilities Index, Gemini 3.1 Pro scores higher (155) than Claude Opus 4.5 (150). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is better for coding, Claude Opus 4.5 or Gemini 3.1 Pro?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Claude Opus 4.5 ranks higher — 72th vs 65th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.